loading

Step 19: Next steps

Noodle is only in its infancy, with the basic framework and enclosure in place there is a lot left to build!


Future I/O

We spent a lot of time exploring computer vision on the Raspberry Pi, but in the short timeline we couldn’t incorporate any libraries. One of the best resources we found was this page describing how to use picamera with OpenCV:
http://tothinkornottothink.com/post/59305587476/raspberry-pi-simplecv-opencv-raspicam-csi-camera

The current code handles these features:

  • microphone
    • detecting loud noise (trigger)
  • audio
    • playing sound file (action)
    • text to speech playback (action)
  • camera
    • take picture (query)

Others we would like to add include:

  • microphone
    • detecting pause / quiet (trigger)
    • capture 5s audio (query)
  • camera
    • detect motion (trigger)
    • detect face (trigger)
    • detect light (trigger)
      • detect dark (trigger)
    • capture video (query)
  • display
    • display text (action)
    • display image (action)
  • gpio
    • pin read (trigger)
    • pin read (query)
    • pin write (action)
  • http
    • url ping (trigger)
    • url ping (query)
    • url ping (action)



How to extend / improve the code

You can fork the code here: https://github.com/lmccart/noodle, and submit pull requests to have your modifications and improvements merged in.

<p>can you answer me please i am in eighth grade and I am making this for language arts. ASAP</p>
<p>how long did this take you</p>
<p>may price more than 10 k INR</p>
<p>What is the total price of this?</p>
<p>i really like the design. very well made! </p>
<p>ain't there a video for it? i wanna see it moving @_@ please :|</p>
Does someone have the message: &quot;Cannot read property 'HITId' of undefined&quot; when executing app.js ?
<p>Have you ever considered turning this into Wheatley from Portal 2? that is my ultimate goal for this.</p>
<p>I did some computer vision on the raspberry pi. For instance face detection and feature tracking. I am working on improving it until it is not using all of the raspi computation power, which is currently the case.</p>
<p>Great project and instructions.</p><p>Im confused on how the noodle actually processes events. What is the response time? Can I make it automated or does it have to have a real person always?</p>
<p>Response time from Mechanical Turk is around 5 minutes, but if you follow this Instructable in general and then substitute your own Turk form that posts directly you a dtabase/service you have set up, then you can get the response time down much lower (maybe 30 seconds).</p><p>Some basic things can be done automatically (like motion detection or basic speech to text) but we were focusing on the manual things.</p>
<p>Am sorry if i skipped but i found no video of your robot. A video would be really nice.</p>
<p>There isn't a video, mainly because the pictures are more representative :) The video would mostly show it playing sounds or putting pictures on the screen, or doing something more digital with the network.</p>
<p>brilliant!</p>
this is amazing! It never ceases to amaze me what people can do with a raspberry pi - you are a genius
<p>Need a video of the robot please!</p>
Oh,so intreseting
<p>Great job!</p>
<p>Amazing. You should enter in a contest. You'll be sure to win something</p>
Love it.

About This Instructable

98,456views

570favorites

License:

More by lmccart:Noodle: a crowdsourced robot 
Add instructable to: